predict.gbts

a model object returned from <code><a rd-options="" href="/link/gbts?package=gbts&version=1.0.1" data-mini-rdoc="gbts::gbts">gbts</a></code>.

object

a data.frame of predictors. It has to follow the same format and
restrictions as the training dataset that generated the model.

an integer of the number of computing cores to be used. If
<code>nwrk</code> is less than the number of available cores on the machine, it
uses all available cores.

nwrk

further arguments passed to or from other methods.


This function generates predictions for a given dataset using the returned
object from <code><a rd-options="" href="/link/gbts?package=gbts&version=1.0.1" data-mini-rdoc="gbts::gbts">gbts</a></code>. It first generates a set of predictions
for each cross-validation model, and then averaging them on the log-odds
scale (for binary classification) or on the response scale (for regression)
to produce the final prediction.


An implementation of hyperparameter optimization for Gradient
Boosted Trees on binary classification and regression problems. The current
version provides two optimization methods: Bayesian optimization and random
search.

Waley J. Liang

gbts

Hyperparameter Search for Gradient Boosted Trees

predict.gbts function

a model object returned from <code><a rd-options='' href='gbts'>gbts</a></code>.


This function generates predictions for a given dataset using the returned
object from <code><a rd-options='' href='gbts'>gbts</a></code>. It first generates a set of predictions
for each cross-validation model, and then averaging them on the log-odds
scale (for binary classification) or on the response scale (for regression)
to produce the final prediction.


predict.gbts: Predict method for optimized Gradient Boosted Trees

Description

Usage

Arguments

Value

See Also